zlacker

>>meetpa+(OP)
Gemini 2.5 pro is great, but also VERY expensive with non opaque cost insights

Just recently a lot of people (me included) got hit with a surprise bill, with some racking up $500 in cost for normal use

I certainly got burnt and removed my API key from my tools to not accidentally use it again

Example: https://x.com/pashmerepat/status/1918084120514900395?s=46

>>artdig+mf1
From the linked tweet the author seems to be using Gemini through another layer called OpenRouter - it seems quite possible that the issue around lack of clarity of billing/caching could be from that extra layer of indirection.

>>danpal+zw1
OpenRouter lets you fund a wallet and spend no more than that. Google will let it go out of control and they purposely delay the billing console by up to 24 hours so if you don't track it all yourself you can get hit big, especially if it is a coding error that uses up to the rate limits.

>>cma+cy1
There are better solutions in the market if you're looking for in-depth observability for LLM inference. For example, use Requesty (requesty at ai) to get very in-depth analytics, breakdowns and logs. You can also set spend limits, create routing policies or allow only a sub-set of models that do not retain data.